1.. SPDX-License-Identifier: GPL-2.0+ 2 3===================================================== 4Linux Driver for Intel(R) Ethernet Network Connection 5===================================================== 6 7Intel Gigabit Linux driver. 8Copyright(c) 2008-2018 Intel Corporation. 9 10Contents 11======== 12 13- Identifying Your Adapter 14- Command Line Parameters 15- Additional Configurations 16- Support 17 18 19Identifying Your Adapter 20======================== 21For information on how to identify your adapter, and for the latest Intel 22network drivers, refer to the Intel Support website: 23https://www.intel.com/support 24 25 26Command Line Parameters 27======================= 28If the driver is built as a module, the following optional parameters are used 29by entering them on the command line with the modprobe command using this 30syntax:: 31 32 modprobe e1000e [<option>=<VAL1>,<VAL2>,...] 33 34There needs to be a <VAL#> for each network port in the system supported by 35this driver. The values will be applied to each instance, in function order. 36For example:: 37 38 modprobe e1000e InterruptThrottleRate=16000,16000 39 40In this case, there are two network ports supported by e1000e in the system. 41The default value for each parameter is generally the recommended setting, 42unless otherwise noted. 43 44NOTE: A descriptor describes a data buffer and attributes related to the data 45buffer. This information is accessed by the hardware. 46 47InterruptThrottleRate 48--------------------- 49:Valid Range: 0,1,3,4,100-100000 50:Default Value: 3 51 52Interrupt Throttle Rate controls the number of interrupts each interrupt 53vector can generate per second. Increasing ITR lowers latency at the cost of 54increased CPU utilization, though it may help throughput in some circumstances. 55 56Setting InterruptThrottleRate to a value greater or equal to 100 57will program the adapter to send out a maximum of that many interrupts 58per second, even if more packets have come in. This reduces interrupt 59load on the system and can lower CPU utilization under heavy load, 60but will increase latency as packets are not processed as quickly. 61 62The default behaviour of the driver previously assumed a static 63InterruptThrottleRate value of 8000, providing a good fallback value for 64all traffic types, but lacking in small packet performance and latency. 65The hardware can handle many more small packets per second however, and 66for this reason an adaptive interrupt moderation algorithm was implemented. 67 68The driver has two adaptive modes (setting 1 or 3) in which 69it dynamically adjusts the InterruptThrottleRate value based on the traffic 70that it receives. After determining the type of incoming traffic in the last 71timeframe, it will adjust the InterruptThrottleRate to an appropriate value 72for that traffic. 73 74The algorithm classifies the incoming traffic every interval into 75classes. Once the class is determined, the InterruptThrottleRate value is 76adjusted to suit that traffic type the best. There are three classes defined: 77"Bulk traffic", for large amounts of packets of normal size; "Low latency", 78for small amounts of traffic and/or a significant percentage of small 79packets; and "Lowest latency", for almost completely small packets or 80minimal traffic. 81 82 - 0: Off 83 Turns off any interrupt moderation and may improve small packet latency. 84 However, this is generally not suitable for bulk throughput traffic due 85 to the increased CPU utilization of the higher interrupt rate. 86 - 1: Dynamic mode 87 This mode attempts to moderate interrupts per vector while maintaining 88 very low latency. This can sometimes cause extra CPU utilization. If 89 planning on deploying e1000e in a latency sensitive environment, this 90 parameter should be considered. 91 - 3: Dynamic Conservative mode (default) 92 In dynamic conservative mode, the InterruptThrottleRate value is set to 93 4000 for traffic that falls in class "Bulk traffic". If traffic falls in 94 the "Low latency" or "Lowest latency" class, the InterruptThrottleRate is 95 increased stepwise to 20000. This default mode is suitable for most 96 applications. 97 - 4: Simplified Balancing mode 98 In simplified mode the interrupt rate is based on the ratio of TX and 99 RX traffic. If the bytes per second rate is approximately equal, the 100 interrupt rate will drop as low as 2000 interrupts per second. If the 101 traffic is mostly transmit or mostly receive, the interrupt rate could 102 be as high as 8000. 103 - 100-100000: 104 Setting InterruptThrottleRate to a value greater or equal to 100 105 will program the adapter to send at most that many interrupts per second, 106 even if more packets have come in. This reduces interrupt load on the 107 system and can lower CPU utilization under heavy load, but will increase 108 latency as packets are not processed as quickly. 109 110NOTE: InterruptThrottleRate takes precedence over the TxAbsIntDelay and 111RxAbsIntDelay parameters. In other words, minimizing the receive and/or 112transmit absolute delays does not force the controller to generate more 113interrupts than what the Interrupt Throttle Rate allows. 114 115RxIntDelay 116---------- 117:Valid Range: 0-65535 (0=off) 118:Default Value: 0 119 120This value delays the generation of receive interrupts in units of 1.024 121microseconds. Receive interrupt reduction can improve CPU efficiency if 122properly tuned for specific network traffic. Increasing this value adds extra 123latency to frame reception and can end up decreasing the throughput of TCP 124traffic. If the system is reporting dropped receives, this value may be set 125too high, causing the driver to run out of available receive descriptors. 126 127CAUTION: When setting RxIntDelay to a value other than 0, adapters may hang 128(stop transmitting) under certain network conditions. If this occurs a NETDEV 129WATCHDOG message is logged in the system event log. In addition, the 130controller is automatically reset, restoring the network connection. To 131eliminate the potential for the hang ensure that RxIntDelay is set to 0. 132 133RxAbsIntDelay 134------------- 135:Valid Range: 0-65535 (0=off) 136:Default Value: 8 137 138This value, in units of 1.024 microseconds, limits the delay in which a 139receive interrupt is generated. This value ensures that an interrupt is 140generated after the initial packet is received within the set amount of time, 141which is useful only if RxIntDelay is non-zero. Proper tuning, along with 142RxIntDelay, may improve traffic throughput in specific network conditions. 143 144TxIntDelay 145---------- 146:Valid Range: 0-65535 (0=off) 147:Default Value: 8 148 149This value delays the generation of transmit interrupts in units of 1.024 150microseconds. Transmit interrupt reduction can improve CPU efficiency if 151properly tuned for specific network traffic. If the system is reporting 152dropped transmits, this value may be set too high causing the driver to run 153out of available transmit descriptors. 154 155TxAbsIntDelay 156------------- 157:Valid Range: 0-65535 (0=off) 158:Default Value: 32 159 160This value, in units of 1.024 microseconds, limits the delay in which a 161transmit interrupt is generated. It is useful only if TxIntDelay is non-zero. 162It ensures that an interrupt is generated after the initial Packet is sent on 163the wire within the set amount of time. Proper tuning, along with TxIntDelay, 164may improve traffic throughput in specific network conditions. 165 166copybreak 167--------- 168:Valid Range: 0-xxxxxxx (0=off) 169:Default Value: 256 170 171The driver copies all packets below or equaling this size to a fresh receive 172buffer before handing it up the stack. 173This parameter differs from other parameters because it is a single (not 1,1,1 174etc.) parameter applied to all driver instances and it is also available 175during runtime at /sys/module/e1000e/parameters/copybreak. 176 177To use copybreak, type:: 178 179 modprobe e1000e.ko copybreak=128 180 181SmartPowerDownEnable 182-------------------- 183:Valid Range: 0,1 184:Default Value: 0 (disabled) 185 186Allows the PHY to turn off in lower power states. The user can turn off this 187parameter in supported chipsets. 188 189KumeranLockLoss 190--------------- 191:Valid Range: 0,1 192:Default Value: 1 (enabled) 193 194This workaround skips resetting the PHY at shutdown for the initial silicon 195releases of ICH8 systems. 196 197IntMode 198------- 199:Valid Range: 0-2 200:Default Value: 0 201 202 +-------+----------------+ 203 | Value | Interrupt Mode | 204 +=======+================+ 205 | 0 | Legacy | 206 +-------+----------------+ 207 | 1 | MSI | 208 +-------+----------------+ 209 | 2 | MSI-X | 210 +-------+----------------+ 211 212IntMode allows load time control over the type of interrupt registered for by 213the driver. MSI-X is required for multiple queue support, and some kernels and 214combinations of kernel .config options will force a lower level of interrupt 215support. 216 217This command will show different values for each type of interrupt:: 218 219 cat /proc/interrupts 220 221CrcStripping 222------------ 223:Valid Range: 0,1 224:Default Value: 1 (enabled) 225 226Strip the CRC from received packets before sending up the network stack. If 227you have a machine with a BMC enabled but cannot receive IPMI traffic after 228loading or enabling the driver, try disabling this feature. 229 230WriteProtectNVM 231--------------- 232:Valid Range: 0,1 233:Default Value: 1 (enabled) 234 235If set to 1, configure the hardware to ignore all write/erase cycles to the 236GbE region in the ICHx NVM (in order to prevent accidental corruption of the 237NVM). This feature can be disabled by setting the parameter to 0 during initial 238driver load. 239 240NOTE: The machine must be power cycled (full off/on) when enabling NVM writes 241via setting the parameter to zero. Once the NVM has been locked (via the 242parameter at 1 when the driver loads) it cannot be unlocked except via power 243cycle. 244 245Debug 246----- 247:Valid Range: 0-16 (0=none,...,16=all) 248:Default Value: 0 249 250This parameter adjusts the level of debug messages displayed in the system logs. 251 252 253Additional Features and Configurations 254====================================== 255 256Jumbo Frames 257------------ 258Jumbo Frames support is enabled by changing the Maximum Transmission Unit (MTU) 259to a value larger than the default value of 1500. 260 261Use the ifconfig command to increase the MTU size. For example, enter the 262following where <x> is the interface number:: 263 264 ifconfig eth<x> mtu 9000 up 265 266Alternatively, you can use the ip command as follows:: 267 268 ip link set mtu 9000 dev eth<x> 269 ip link set up dev eth<x> 270 271This setting is not saved across reboots. The setting change can be made 272permanent by adding 'MTU=9000' to the file: 273 274- For RHEL: /etc/sysconfig/network-scripts/ifcfg-eth<x> 275- For SLES: /etc/sysconfig/network/<config_file> 276 277NOTE: The maximum MTU setting for Jumbo Frames is 8996. This value coincides 278with the maximum Jumbo Frames size of 9018 bytes. 279 280NOTE: Using Jumbo frames at 10 or 100 Mbps is not supported and may result in 281poor performance or loss of link. 282 283NOTE: The following adapters limit Jumbo Frames sized packets to a maximum of 2844088 bytes: 285 286 - Intel(R) 82578DM Gigabit Network Connection 287 - Intel(R) 82577LM Gigabit Network Connection 288 289The following adapters do not support Jumbo Frames: 290 291 - Intel(R) PRO/1000 Gigabit Server Adapter 292 - Intel(R) PRO/1000 PM Network Connection 293 - Intel(R) 82562G 10/100 Network Connection 294 - Intel(R) 82562G-2 10/100 Network Connection 295 - Intel(R) 82562GT 10/100 Network Connection 296 - Intel(R) 82562GT-2 10/100 Network Connection 297 - Intel(R) 82562V 10/100 Network Connection 298 - Intel(R) 82562V-2 10/100 Network Connection 299 - Intel(R) 82566DC Gigabit Network Connection 300 - Intel(R) 82566DC-2 Gigabit Network Connection 301 - Intel(R) 82566DM Gigabit Network Connection 302 - Intel(R) 82566MC Gigabit Network Connection 303 - Intel(R) 82566MM Gigabit Network Connection 304 - Intel(R) 82567V-3 Gigabit Network Connection 305 - Intel(R) 82577LC Gigabit Network Connection 306 - Intel(R) 82578DC Gigabit Network Connection 307 308NOTE: Jumbo Frames cannot be configured on an 82579-based Network device if 309MACSec is enabled on the system. 310 311 312ethtool 313------- 314The driver utilizes the ethtool interface for driver configuration and 315diagnostics, as well as displaying statistical information. The latest ethtool 316version is required for this functionality. Download it at: 317 318https://www.kernel.org/pub/software/network/ethtool/ 319 320NOTE: When validating enable/disable tests on some parts (for example, 82578), 321it is necessary to add a few seconds between tests when working with ethtool. 322 323 324Speed and Duplex Configuration 325------------------------------ 326In addressing speed and duplex configuration issues, you need to distinguish 327between copper-based adapters and fiber-based adapters. 328 329In the default mode, an Intel(R) Ethernet Network Adapter using copper 330connections will attempt to auto-negotiate with its link partner to determine 331the best setting. If the adapter cannot establish link with the link partner 332using auto-negotiation, you may need to manually configure the adapter and link 333partner to identical settings to establish link and pass packets. This should 334only be needed when attempting to link with an older switch that does not 335support auto-negotiation or one that has been forced to a specific speed or 336duplex mode. Your link partner must match the setting you choose. 1 Gbps speeds 337and higher cannot be forced. Use the autonegotiation advertising setting to 338manually set devices for 1 Gbps and higher. 339 340Speed, duplex, and autonegotiation advertising are configured through the 341ethtool utility. 342 343Caution: Only experienced network administrators should force speed and duplex 344or change autonegotiation advertising manually. The settings at the switch must 345always match the adapter settings. Adapter performance may suffer or your 346adapter may not operate if you configure the adapter differently from your 347switch. 348 349An Intel(R) Ethernet Network Adapter using fiber-based connections, however, 350will not attempt to auto-negotiate with its link partner since those adapters 351operate only in full duplex and only at their native speed. 352 353 354Enabling Wake on LAN (WoL) 355-------------------------- 356WoL is configured through the ethtool utility. 357 358WoL will be enabled on the system during the next shut down or reboot. For 359this driver version, in order to enable WoL, the e1000e driver must be loaded 360prior to shutting down or suspending the system. 361 362NOTE: Wake on LAN is only supported on port A for the following devices: 363- Intel(R) PRO/1000 PT Dual Port Network Connection 364- Intel(R) PRO/1000 PT Dual Port Server Connection 365- Intel(R) PRO/1000 PT Dual Port Server Adapter 366- Intel(R) PRO/1000 PF Dual Port Server Adapter 367- Intel(R) PRO/1000 PT Quad Port Server Adapter 368- Intel(R) Gigabit PT Quad Port Server ExpressModule 369 370 371Support 372======= 373For general information, go to the Intel support website at: 374https://www.intel.com/support/ 375 376If an issue is identified with the released source code on a supported kernel 377with a supported adapter, email the specific information related to the issue 378to intel-wired-lan@lists.osuosl.org. 379